神经网络动态模型在建筑物裂缝演变预测中的应用

APPLICATION STUDY OF DYNAMIC MODEL CREATED BY ARTIFICIAL NEURAL NETWORK IN PREDICT OF BUILDINGS’ CRACK

探讨了人工神经网络用于建筑物裂缝演变过程的非线性动力学建模的可行性、数学依据、实现方法 ,通过工程实例 ,实现了裂缝演变的自适应在线预测 ,结果说明此方法具有较高的预测精度 ,比传统建模方法有明显的优越性 。

To setting up the nonlinear and dynamic model of the crack of buildings,the feasibility,Math's foundation and the method of realization of Artificial Neural Network (ANN) are studied in this paper.The application of the created model for the real example of engineering illuminates that the model's precision of forecast is excellent,the advantage is obvious to the common Math's method and the practical value in engineering is good.